v2.0.0 shipped · MIT · works with 6 agents

One shared memory for
every AI coding agent.

Switch from Codex to Claude to Antigravity, or come back tomorrow after a usage limit, and your agent already knows what you're building, where you are, and what's next. No re-explaining.

PS>irm https://raw.githubusercontent.com/AnasNafees1802/continuum/main/bootstrap.ps1 | iex

Installs once, for every agent on your machine. No runtime. No service. Plain Markdown + JSON.

Speaks the protocol to Claude Code Codex Antigravity Gemini CLI Cursor Windsurf
The problem

Context is trapped in silos.

Every agent keeps its own private history, and none of them share.

😤 Without Continuum

You ship a couple of features, then the daily limit hits and your agent stops. You switch to another one, but it knows nothing. You burn time and tokens re-explaining the project, and you lose the thread of why things were done a certain way.

🔁 With Continuum

A small, structured memory ledger lives inside your repo at .aicontext/. Every agent follows one rule: read it when you start, update it before you stop. Because the memory isn't trapped in any one tool, context survives the switch.

How it works

Three moments, on autopilot.

Native hooks fire them for you, so continuity never depends on anyone remembering.

📍
01 · SESSION START

Catch up

A session-start hook injects STATE.md into context and verifies it against git. Your agent briefs you before you type a word.

✍️
02 · DURING WORK

Keep it live

Tasks and decisions stay current as you go. A pre-compaction hook prompts a handoff right as the context window fills, while the detail still exists.

💾
03 · HANDOFF

Save the thread

One command stamps the ledger + git commit. And if a crash beats you to it, continuum import reconstructs the session from the transcript, plus git.

See it

Open a fresh session. Ask one question.

No context pasted. No project explained. It just knows.

claude, ~/my-project
you › so where are we? - reconciling ledger against git before briefing - 📍 Caught up from .aicontext/ • Building: auth flow with token refresh • Status: login + session store done; refresh half-wired • Next: finish token refresh in src/auth/refresh.ts ⚠ verify: 3 commits landed since the last save, reconciled, ledger is accurate. Want me to pick up the token refresh where Codex left off?
Why it holds up

Built for the moment it matters.

The naïve version breaks exactly when a usage limit kills the session. Continuum doesn't rely on remembering.

🪝

Deterministic hooks

Catch-up, handoff, and a one-per-session nudge fire automatically, on Claude Code, Codex, Gemini and Cursor. Not a polite request to the model.

⏮️

Reconstruction

A limit-killed session is rebuilt from the last agent's own transcript plus a git view, even across a Codex ⇄ Claude switch.

🧭

Never trusts a stale ledger

Catch-up compares the saved commit to HEAD and flags drift, so an agent verifies against git instead of briefing you wrong.

🛟

Universal git floor

Even where hooks or transcripts aren't available, git-based reconstruction rebuilds "what changed." Continuity never fully fails, on any tool.

🔒

Atomic, portable writes

Every ledger write is atomic and BOM-free, no truncated files, and JSON that every tool's parser can read. Cross-tool by construction.

🍃

Zero dependencies

Plain PowerShell + bash and Markdown + JSON. No runtime, no service, no lock-in. Readable and editable by hand.

Cross-agent support

What's automated, per agent.

Honest status, verified means confirmed on a real session.

AgentCatch-upHandoffStop nudgeReconstructionStatus
Claude Code✓ hooknative● verified
Codex✓ hooknative● verified
Antigravity✓ protocol--git● verified
Gemini CLI✓ hook-native● beta
Cursor✓ hookgit● beta
Windsurf✓ per-turn--git● beta

Every agent also participates via the honor-protocol (AGENTS.md / GEMINI.md / rules) and the universal git floor.

Bonus

It saves tokens, not just time.

Real, structural savings. No fuzzy benchmarks, just less waste.

🗣️

No re-explaining

Catch-up injects a compact summary (a few hundred tokens) instead of you re-pasting the whole project into a fresh session every time.

↩️

No redone work

A session killed by a usage limit gets reconstructed, not repeated. Redoing a whole session is the most expensive waste there is.

✂️

Bounded context

Journal rotation keeps the ledger small, so the memory never bloats the very context window it exists to save.

Install

Up and running in one step.

Pick whichever suits you. All three do the same thing, and the memory ledger is created automatically the first time an agent opens a project.

1

Let your AI agent install it

Easiest
Install "Continuum" globally on my machine. It's an open-source (MIT) tool that gives AI coding agents a shared memory so they keep context across sessions and tools: https://github.com/AnasNafees1802/continuum

1. Detect my operating system.
2. On Windows, run in PowerShell:
   irm https://raw.githubusercontent.com/AnasNafees1802/continuum/main/bootstrap.ps1 | iex
   On macOS or Linux, run in bash:
   curl -fsSL https://raw.githubusercontent.com/AnasNafees1802/continuum/main/bootstrap.sh | bash
3. When it finishes, tell me which agents it set up and remind me to restart any open agent sessions.

Do not change anything else.

Paste this into Claude Code, Codex, Cursor, Gemini or any coding agent. It will ask you to approve the command. Approve it, and you are done.

2

One line in your terminal

PS>irm https://raw.githubusercontent.com/AnasNafees1802/continuum/main/bootstrap.ps1 | iex
3

Clone and run it yourself

git clone https://github.com/AnasNafees1802/continuum.git
cd continuum
# Windows:      powershell -ExecutionPolicy Bypass -File .\install-global.ps1
# macOS/Linux:  bash ./install-global.sh

Want to read the code before running anything? See all install options on GitHub.

Then open any project in any agent. It reads .aicontext/STATE.md and catches you up automatically.

Stop re-explaining your project.

Give every AI agent one shared brain. It's open source, MIT, and installs in one line.